run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-27 19:30:01 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

LaamaParse: v2 documentation is all wrong #580

New Issue
Closed
opened 2026-02-16 00:18:19 -05:00 by yindo · 2 comments
yindo commented 2026-02-16 00:18:19 -05:00
Owner
Copy Link
Copy Source

Originally created by @adadgio on GitHub (Dec 8, 2025).

Describe the bug

The V2 Parse API documentation has mistakes:

https://developers.llamaindex.ai/typescript/cloud/llamaparse/v2/api-v2-guide/#url-parsing-example

States:

"source_url": "https://example.com/report.pdf",
"http_proxy": "https://proxy.example.com",
"tier": "cost_effective",
"version": "latest",
...

It's in fact:

{
"source_url": "https://example.com/report.pdf",
"parse_options": {
   "tier: "cost_effective",
    "version": "latest",
  },
...
}

Client:

  • API

Additional context
So many part of the documentation are like that. To the point of making it practialy unusable because we spend to much time looking for the source of truth. Webhook with the new configurations are also not send with the V2, whereas they worked on the v1 API endpoint. On a side node, it states that the v2 was also made to have clearer error messages:

{"detail":[{"type":"missing","loc":["body","parse_options","tier"],"msg":"Field required","input":{}}]}

This does not mean anything and has no informative value whatsoever. What is "body" (it's not a field), why are "tier" and "parse_option" at the same error level when on should not exist and the other one is missing? Etc...

Image This is JUST the requests made to try navigate through a working version with the provided documentation. I'll have to wait next month to just test a real pipeline I guess...

API documentation:

webhook_configurations: [
    { webhook_url: "my url...", webhook_event: [ "parse.done" ] }
]

Job ID logs:

Image
Originally created by @adadgio on GitHub (Dec 8, 2025). **Describe the bug** The V2 Parse API documentation has mistakes: https://developers.llamaindex.ai/typescript/cloud/llamaparse/v2/api-v2-guide/#url-parsing-example States: ``` "source_url": "https://example.com/report.pdf", "http_proxy": "https://proxy.example.com", "tier": "cost_effective", "version": "latest", ... ``` It's in fact: ``` { "source_url": "https://example.com/report.pdf", "parse_options": { "tier: "cost_effective", "version": "latest", }, ... } ``` **Client:** - API **Additional context** So many part of the documentation are like that. To the point of making it practialy unusable because we spend to much time looking for the source of truth. Webhook with the new configurations are also not send with the V2, whereas they worked on the v1 API endpoint. On a side node, it states that the v2 was also made to have clearer error messages: `{"detail":[{"type":"missing","loc":["body","parse_options","tier"],"msg":"Field required","input":{}}]} ` This does not mean anything and has no informative value whatsoever. What is "body" (it's not a field), why are "tier" and "parse_option" at the same error level when on should not exist and the other one is missing? Etc... <img width="977" height="166" alt="Image" src="https://github.com/user-attachments/assets/c212524c-9f4f-4793-8b79-0f517841fa55" /> This is JUST the requests made to try navigate through a working version with the provided documentation. I'll have to wait next month to just test a real pipeline I guess... API documentation: ``` webhook_configurations: [ { webhook_url: "my url...", webhook_event: [ "parse.done" ] } ] ``` Job ID logs: <img width="654" height="183" alt="Image" src="https://github.com/user-attachments/assets/2b44d1c2-e822-45f8-a02f-fc515162306d" />
yindo added the bug label 2026-02-16 00:18:19 -05:00
yindo closed this issue 2026-02-16 00:18:19 -05:00
yindo commented 2026-02-16 00:18:20 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Dec 8, 2025):

The doc was actually released before the code. Please note this is an alpha version and it should be used in prod yet.

For clarification body is the body of the HTTP request (in this case, the config object).

@BinaryBrain commented on GitHub (Dec 8, 2025): The doc was actually released before the code. Please note this is an alpha version and it should be used in prod yet. For clarification `body` is the body of the HTTP request (in this case, the config object).
yindo commented 2026-02-16 00:18:20 -05:00
Author
Owner
Copy Link
Copy Source

@adadgio commented on GitHub (Dec 8, 2025):

So, which part of the documentation is correct ? Why is it still referenced?

Another note: it's the same with the v1, I tried to switch to v2 because i had the same type of issues with the v1 (docs and examples not matching API): https://github.com/run-llama/llama_cloud_services/issues/1049

@adadgio commented on GitHub (Dec 8, 2025): So, which part of the documentation is correct ? Why is it still referenced? Another note: it's the same with the v1, I tried to switch to v2 because i had the same type of issues with the v1 (docs and examples not matching API): https://github.com/run-llama/llama_cloud_services/issues/1049
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#580
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?